Job Description:

Job Role:

Senior Infrastructure Engineer / Platform Engineer AI Platforms & GPU Infrastructure

Job Summary:

We are looking for a hands-on Infrastructure Engineer / Platform Engineer with 8+ years of experience building and operating cloud-native platforms for Agentic AI workloads. The ideal candidate should have deep expertise in Kubernetes, Terraform, CI/CD, Infrastructure as Code, Multi-Cloud environments, and proven experience deploying Generative AI, Agentic AI, and LLM workloads on GPU infrastructure. Experience supporting production-scale AI platforms, model serving, and MLOps is essential.

Key Responsibilities:

- Design, build, and operate scalable Kubernetes platforms for AI/ML and GenAI workloads.

- Automate cloud infrastructure provisioning using Terraform and Infrastructure as Code.

- Build and maintain CI/CD pipelines and GitOps deployment frameworks.

- Deploy and manage GPU-enabled infrastructure supporting model training and inference.

- Support Large Language Models (LLMs), RAG pipelines, and Agentic AI applications in production.

- Build scalable AI serving platforms using Kubernetes-based model serving frameworks.

- Implement monitoring, observability, security, and platform reliability best practices.

- Partner with AI/ML engineers and data scientists to accelerate AI adoption.

- Drive platform automation and self-service capabilities across cloud environments.

Required Skills:

- 8+ years of experience in Platform Engineering

- Strong hands-on experience with Kubernetes in large-scale production environments.

- Expertise in Terraform and Infrastructure as Code (IaC).

- Strong experience with CI/CD, GitOps, and automation.

- Experience across AWS, Azure, and/or GCP environments.

- Strong Linux administration and troubleshooting skills.

- Proficiency in Python and/or Go.

Mandatory Experience:

- Hands-on experience deploying AI/ML, Generative AI, or Agentic AI solutions in production.

- Experience deploying and scaling LLM workloads.

- Strong experience with GPU infrastructure including NVIDIA GPUs, CUDA, GPU Operators, and model optimization.

- Experience with AI model serving platforms such as Triton Inference Server, KServe, Ray Serve, or similar.

- Experience building RAG pipelines and AI platforms.

- Experience with vector databases and AI orchestration frameworks.